当前期刊: arXiv - CS - Machine Learning Go to current issue    加入关注   
显示样式:        排序: IF: - GO 导出
我的关注
我的收藏
您暂时未登录!
登录
  • Mining Documentation to Extract Hyperparameter Schemas
    arXiv.cs.LG Pub Date : 2020-06-30
    Guillaume Baudart; Peter D. Kirchner; Martin Hirzel; Kiran Kate

    AI automation tools need machine-readable hyperparameter schemas to define their search spaces. At the same time, AI libraries often come with good human-readable documentation. While such documentation contains most of the necessary information, it is unfortunately not ready to consume by tools. This paper describes how to automatically mine Python docstrings in AI libraries to extract JSON Schemas

    更新日期:2020-07-01
  • Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules
    arXiv.cs.LG Pub Date : 2020-06-30
    Sarthak Mittal; Alex Lamb; Anirudh Goyal; Vikram Voleti; Murray Shanahan; Guillaume Lajoie; Michael Mozer; Yoshua Bengio

    Robust perception relies on both bottom-up and top-down signals. Bottom-up signals consist of what's directly observed through sensation. Top-down signals consist of beliefs and expectations based on past experience and short-term memory, such as how the phrase `peanut butter and~...' will be completed. The optimal combination of bottom-up and top-down information remains an open question, but the

    更新日期:2020-07-01
  • Improving robustness against common corruptions by covariate shift adaptation
    arXiv.cs.LG Pub Date : 2020-06-30
    Steffen Schneider; Evgenia Rusak; Luisa Eck; Oliver Bringmann; Wieland Brendel; Matthias Bethge

    Today's state-of-the-art machine vision models are vulnerable to image corruptions like blurring or compression artefacts, limiting their performance in many real-world applications. We here argue that popular benchmarks to measure model robustness against common corruptions (like ImageNet-C) underestimate model robustness in many (but not all) application scenarios. The key insight is that in many

    更新日期:2020-07-01
  • Evaluating the Performance of Reinforcement Learning Algorithms
    arXiv.cs.LG Pub Date : 2020-06-30
    Scott M. Jordan; Yash Chandak; Daniel Cohen; Mengxue Zhang; Philip S. Thomas

    Performance evaluations are critical for quantifying algorithmic advances in reinforcement learning. Recent reproducibility analyses have shown that reported performance results are often inconsistent and difficult to replicate. In this work, we argue that the inconsistency of performance stems from the use of flawed evaluation metrics. Taking a step towards ensuring that reported results are consistent

    更新日期:2020-07-01
  • Sampling from a $k$-DPP without looking at all items
    arXiv.cs.LG Pub Date : 2020-06-30
    Daniele Calandriello; Michał Dereziński; Michal Valko

    Determinantal point processes (DPPs) are a useful probabilistic model for selecting a small diverse subset out of a large collection of items, with applications in summarization, stochastic optimization, active learning and more. Given a kernel function and a subset size $k$, our goal is to sample $k$ out of $n$ items with probability proportional to the determinant of the kernel matrix induced by

    更新日期:2020-07-01
  • Tomographic Auto-Encoder: Unsupervised Bayesian Recovery of Corrupted Data
    arXiv.cs.LG Pub Date : 2020-06-30
    Francesco Tonolini; Pablo G. Moreno; Andreas Damianou; Roderick Murray-Smith

    We propose a new probabilistic method for unsupervised recovery of corrupted data. Given a large ensemble of degraded samples, our method recovers accurate posteriors of clean values, allowing the exploration of the manifold of possible reconstructed data and hence characterising the underlying uncertainty. In this setting, direct application of classical variational methods often gives rise to collapsed

    更新日期:2020-07-01
  • MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning
    arXiv.cs.LG Pub Date : 2020-06-30
    Elise van der Pol; Daniel E. Worrall; Herke van Hoof; Frans A. Oliehoek; Max Welling

    This paper introduces MDP homomorphic networks for deep reinforcement learning. MDP homomorphic networks are neural networks that are equivariant under symmetries in the joint state-action space of an MDP. Current approaches to deep reinforcement learning do not usually exploit knowledge about such structure. By building this prior knowledge into policy and value networks using an equivariance constraint

    更新日期:2020-07-01
  • Graph Clustering with Graph Neural Networks
    arXiv.cs.LG Pub Date : 2020-06-30
    Anton Tsitsulin; John Palowitch; Bryan Perozzi; Emmanuel Müller

    Graph Neural Networks (GNNs) have achieved state-of-the-art results on many graph analysis tasks such as node classification and link prediction. However, important unsupervised problems on graphs, such as graph clustering, have proved more resistant to advances in GNNs. In this paper, we study unsupervised training of GNN pooling in terms of their clustering capabilities. We start by drawing a connection

    更新日期:2020-07-01
  • Deriving Neural Network Design and Learning from the Probabilistic Framework of Chain Graphs
    arXiv.cs.LG Pub Date : 2020-06-30
    Yuesong Shen; Daniel Cremers

    The last decade has witnessed a boom of neural network (NN) research and applications achieving state-of-the-art results in various domains. Yet, most advances on architecture and learning have been discovered empirically in a trial-and-error manner such that a more systematic exploration is difficult. Their theoretical analyses are limited and a unifying framework is absent. In this paper, we tackle

    更新日期:2020-07-01
  • Guided Learning of Nonconvex Models through Successive Functional Gradient Optimization
    arXiv.cs.LG Pub Date : 2020-06-30
    Rie Johnson; Tong Zhang

    This paper presents a framework of successive functional gradient optimization for training nonconvex models such as neural networks, where training is driven by mirror descent in a function space. We provide a theoretical analysis and empirical study of the training method derived from this framework. It is shown that the method leads to better performance than that of standard training techniques

    更新日期:2020-07-01
  • Path Integral Based Convolution and Pooling for Graph Neural Networks
    arXiv.cs.LG Pub Date : 2020-06-29
    Zheng Ma; Junyu Xuan; Yu Guang Wang; Ming Li; Pietro Lio

    Graph neural networks (GNNs) extends the functionality of traditional neural networks to graph-structured data. Similar to CNNs, an optimized design of graph convolution and pooling is key to success. Borrowing ideas from physics, we propose a path integral based graph neural networks (PAN) for classification and regression tasks on graphs. Specifically, we consider a convolution operation that involves

    更新日期:2020-07-01
  • Random Partitioning Forest for Point-Wise and Collective Anomaly Detection -- Application to Intrusion Detection
    arXiv.cs.LG Pub Date : 2020-06-29
    Pierre-Francois Marteau

    In this paper, we propose DiFF-RF, an ensemble approach composed of random partitioning binary trees to detect point-wise and collective (as well as contextual) anomalies. Thanks to a distance-based paradigm used at the leaves of the trees, this semi-supervised approach solves a drawback that has been identified in the isolation forest (IF) algorithm. Moreover, taking into account the frequencies of

    更新日期:2020-07-01
  • Incremental Training of a Recurrent Neural Network Exploiting a Multi-Scale Dynamic Memory
    arXiv.cs.LG Pub Date : 2020-06-29
    Antonio Carta; Alessandro Sperduti; Davide Bacciu

    The effectiveness of recurrent neural networks can be largely influenced by their ability to store into their dynamical memory information extracted from input sequences at different frequencies and timescales. Such a feature can be introduced into a neural architecture by an appropriate modularization of the dynamic memory. In this paper we propose a novel incrementally trained recurrent architecture

    更新日期:2020-07-01
  • Counterfactual explanation of machine learning survival models
    arXiv.cs.LG Pub Date : 2020-06-26
    Maxim S. Kovalev; Lev V. Utkin

    A method for counterfactual explanation of machine learning survival models is proposed. One of the difficulties of solving the counterfactual explanation problem is that the classes of examples are implicitly defined through outcomes of a machine learning survival model in the form of survival functions. A condition that establishes the difference between survival functions of the original example

    更新日期:2020-07-01
  • Causality Learning: A New Perspective for Interpretable Machine Learning
    arXiv.cs.LG Pub Date : 2020-06-27
    Guandong Xu; Tri Dung Duong; Qian Li; Shaowu Liu; Xianzhi Wang

    Recent years have witnessed the rapid growth of machine learning in a wide range of fields such as image recognition, text classification, credit scoring prediction, recommendation system, etc. In spite of their great performance in different sectors, researchers still concern about the mechanism under any machine learning (ML) techniques that are inherently black-box and becoming more complex to achieve

    更新日期:2020-07-01
  • Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning
    arXiv.cs.LG Pub Date : 2020-06-28
    Lionel Blondé; Pablo Strasser; Alexandros Kalousis

    Despite the recent success of reinforcement learning in various domains, these approaches remain, for the most part, deterringly sensitive to hyper-parameters and are often riddled with essential engineering feats allowing their success. We consider the case of off-policy generative adversarial imitation learning, and perform an in-depth review, qualitative and quantitative, of the method. Crucially

    更新日期:2020-07-01
  • Federated Mutual Learning
    arXiv.cs.LG Pub Date : 2020-06-27
    Tao Shen; Jie Zhang; Xinkang Jia; Fengda Zhang; Gang Huang; Pan Zhou; Fei Wu; Chao Wu

    Federated learning enables collaboratively training machine learning models on decentralized data. The three types of heterogeneous natures that is data, model, and objective bring about unique challenges to the canonical federated learning algorithm (FederatedAveraging), where one shared model is produced by and for all clients. First, due to the Non-IIDness of data, the global shared model may perform

    更新日期:2020-07-01
  • On the Applicability of ML Fairness Notions
    arXiv.cs.LG Pub Date : 2020-06-30
    Karima Makhlouf; Sami Zhioua; Catuscia Palamidessi

    ML-based predictive systems are increasingly used to support decisions with a critical impact on individuals' lives such as college admission, job hiring, child custody, criminal risk assessment, etc. As a result, fairness emerged as an important requirement to guarantee that predictive systems do not discriminate against specific individuals or entire sub-populations, in particular, minorities. Given

    更新日期:2020-07-01
  • Optimal Rates of Distributed Regression with Imperfect Kernels
    arXiv.cs.LG Pub Date : 2020-06-30
    Hongwei SunUniversity of Jinan; Qiang WuMiddle Tennessee State University

    Distributed machine learning systems have been receiving increasing attentions for their efficiency to process large scale data. Many distributed frameworks have been proposed for different machine learning tasks. In this paper, we study the distributed kernel regression via the divide and conquer approach. This approach has been proved asymptotically minimax optimal if the kernel is perfectly selected

    更新日期:2020-07-01
  • Overview of Gaussian process based multi-fidelity techniques with variable relationship between fidelities
    arXiv.cs.LG Pub Date : 2020-06-30
    Loïc Brevault; Mathieu Balesdent; Ali Hebbal

    The design process of complex systems such as new configurations of aircraft or launch vehicles is usually decomposed in different phases which are characterized for instance by the depth of the analyses in terms of number of design variables and fidelity of the physical models. At each phase, the designers have to compose with accurate but computationally intensive models as well as cheap but inaccurate

    更新日期:2020-07-01
  • Neural Datalog Through Time: Informed Temporal Modeling via Logical Specification
    arXiv.cs.LG Pub Date : 2020-06-30
    Hongyuan Mei; Guanghui Qin; Minjie Xu; Jason Eisner

    Learning how to predict future events from patterns of past events is difficult when the set of possible event types is large. Training an unrestricted neural model might overfit to spurious patterns. To exploit domain-specific knowledge of how past events might affect an event's present probability, we propose using a temporal deductive database to track structured facts over time. Rules serve to

    更新日期:2020-07-01
  • Model-based Reinforcement Learning: A Survey
    arXiv.cs.LG Pub Date : 2020-06-30
    Thomas M. Moerland; Joost Broekens; Catholijn M. Jonker

    Sequential decision making, commonly formalized as Markov Decision Process (MDP) optimization, is a key challenge in artificial intelligence. Two key approaches to this problem are reinforcement learning (RL) and planning. This paper presents a survey of the integration of both fields, better known as model-based reinforcement learning. Model-based RL has two main steps. First, we systematically cover

    更新日期:2020-07-01
  • Hierarchical Qualitative Clustering -- clustering mixed datasets with critical qualitative information
    arXiv.cs.LG Pub Date : 2020-06-30
    Diogo Seca; João Mendes-Moreira; Tiago Mendes-Neves; Ricardo Sousa

    Clustering can be used to extract insights from data or to verify some of the assumptions held by the domain experts, namely data segmentation. In the literature, few methods can be applied in clustering qualitative values using the context associated with other variables present in the data, without losing interpretability. Moreover, the metrics for calculating dissimilarity between qualitative values

    更新日期:2020-07-01
  • R2-B2: Recursive Reasoning-Based Bayesian Optimization for No-Regret Learning in Games
    arXiv.cs.LG Pub Date : 2020-06-30
    Zhongxiang Dai; Yizhou Chen; Kian Hsiang Low; Patrick Jaillet; Teck-Hua Ho

    This paper presents a recursive reasoning formalism of Bayesian optimization (BO) to model the reasoning process in the interactions between boundedly rational, self-interested agents with unknown, complex, and costly-to-evaluate payoff functions in repeated games, which we call Recursive Reasoning-Based BO (R2-B2). Our R2-B2 algorithm is general in that it does not constrain the relationship among

    更新日期:2020-07-01
  • Constructive Universal High-Dimensional Distribution Generation through Deep ReLU Networks
    arXiv.cs.LG Pub Date : 2020-06-30
    Dmytro Perekrestenko; Stephan Müller; Helmut Bölcskei

    We present an explicit deep neural network construction that transforms uniformly distributed one-dimensional noise into an arbitrarily close approximation of any two-dimensional Lipschitz-continuous target distribution. The key ingredient of our design is a generalization of the "space-filling" property of sawtooth functions discovered in (Bailey & Telgarsky, 2018). We elicit the importance of depth

    更新日期:2020-07-01
  • Involutive MCMC: a Unifying Framework
    arXiv.cs.LG Pub Date : 2020-06-30
    Kirill Neklyudov; Max Welling; Evgenii Egorov; Dmitry Vetrov

    Markov Chain Monte Carlo (MCMC) is a computational approach to fundamental problems such as inference, integration, optimization, and simulation. The field has developed a broad spectrum of algorithms, varying in the way they are motivated, the way they are applied and how efficiently they sample. Despite all the differences, many of them share the same core principle, which we unify as the Involutive

    更新日期:2020-07-01
  • Training highly effective connectivities within neural networks with randomly initialized, fixed weights
    arXiv.cs.LG Pub Date : 2020-06-30
    Cristian Ivan; Razvan Florian

    We present some novel, straightforward methods for training the connection graph of a randomly initialized neural network without training the weights. These methods do not use hyperparameters defining cutoff thresholds and therefore remove the need for iteratively searching optimal values of such hyperparameters. We can achieve similar or higher performances than in the case of training all weights

    更新日期:2020-07-01
  • Understanding Diversity based Pruning of Neural Networks -- Statistical Mechanical Analysis
    arXiv.cs.LG Pub Date : 2020-06-30
    Rupam Acharyya; Boyu Zhang; Ankani Chattoraj; Shouman Das; Daniel Stefankovic

    Deep learning architectures with a huge number of parameters are often compressed using pruning techniques to ensure computational efficiency of inference during deployment. Despite multitude of empirical advances, there is no theoretical understanding of the effectiveness of different pruning methods. We address this issue by setting up the problem in the statistical mechanics formulation of a teacher-student

    更新日期:2020-07-01
  • Forced-exploration free Strategies for Unimodal Bandits
    arXiv.cs.LG Pub Date : 2020-06-30
    Hassan SaberSEQUEL; Pierre MénardSEQUEL; Odalric-Ambrym MaillardSEQUEL

    We consider a multi-armed bandit problem specified by a set of Gaussian or Bernoulli distributions endowed with a unimodal structure. Although this problem has been addressed in the literature (Combes and Proutiere, 2014), the state-of-the-art algorithms for such structure make appear a forced-exploration mechanism. We introduce IMED-UB, the first forced-exploration free strategy that exploits the

    更新日期:2020-07-01
  • Enabling Continual Learning with Differentiable Hebbian Plasticity
    arXiv.cs.LG Pub Date : 2020-06-30
    Vithursan Thangarasa; Thomas Miconi; Graham W. Taylor

    Continual learning is the problem of sequentially learning new tasks or knowledge while protecting previously acquired knowledge. However, catastrophic forgetting poses a grand challenge for neural networks performing such learning process. Thus, neural networks that are deployed in the real world often struggle in scenarios where the data distribution is non-stationary (concept drift), imbalanced

    更新日期:2020-07-01
  • Graph Neural Networks for Leveraging Industrial Equipment Structure: An application to Remaining Useful Life Estimation
    arXiv.cs.LG Pub Date : 2020-06-30
    Jyoti Narwariya; Pankaj Malhotra; Vishnu TV; Lovekesh Vig; Gautam Shroff

    Automated equipment health monitoring from streaming multisensor time-series data can be used to enable condition-based maintenance, avoid sudden catastrophic failures, and ensure high operational availability. We note that most complex machinery has a well-documented and readily accessible underlying structure capturing the inter-dependencies between sub-systems or modules. Deep learning models such

    更新日期:2020-07-01
  • AdaSGD: Bridging the gap between SGD and Adam
    arXiv.cs.LG Pub Date : 2020-06-30
    Jiaxuan Wang; Jenna Wiens

    In the context of stochastic gradient descent(SGD) and adaptive moment estimation (Adam),researchers have recently proposed optimization techniques that transition from Adam to SGD with the goal of improving both convergence and generalization performance. However, precisely how each approach trades off early progress and generalization is not well understood; thus, it is unclear when or even if, one

    更新日期:2020-07-01
  • Associative Memory in Iterated Overparameterized Sigmoid Autoencoders
    arXiv.cs.LG Pub Date : 2020-06-30
    Yibo Jiang; Cengiz Pehlevan

    Recent work showed that overparameterized autoencoders can be trained to implement associative memory via iterative maps, when the trained input-output Jacobian of the network has all of its eigenvalue norms strictly below one. Here, we theoretically analyze this phenomenon for sigmoid networks by leveraging recent developments in deep learning theory, especially the correspondence between training

    更新日期:2020-07-01
  • Theory-Inspired Path-Regularized Differential Network Architecture Search
    arXiv.cs.LG Pub Date : 2020-06-30
    Pan Zhou; Caiming Xiong; Richard Socher; Steven C. H. Hoi

    Despite its high search efficiency, differential architecture search (DARTS) often selects network architectures with dominated skip connections which lead to performance degradation. However, theoretical understandings on this issue remain absent, hindering the development of more advanced methods in a principled way. In this work, we solve this problem by theoretically analyzing the effects of various

    更新日期:2020-07-01
  • Sliced Kernelized Stein Discrepancy
    arXiv.cs.LG Pub Date : 2020-06-30
    Wenbo Gong; Yingzhen Li; José Miguel Hernández-Lobato

    Kernelized Stein discrepancy (KSD), though being extensively used in goodness-of-fit tests and model learning, suffers from the curse-of-dimensionality. We address this issue by proposing the sliced Stein discrepancy and its scalable and kernelized variants, which employs kernel-based test functions defined on the optimal onedimensional projections instead of the full input in high dimensions. When

    更新日期:2020-07-01
  • Maximum Entropy Models for Fast Adaptation
    arXiv.cs.LG Pub Date : 2020-06-30
    Samarth Sinha; Anirudh Goyal; Animesh Garg

    Deep Neural Networks have shown great promise on a variety of downstream tasks; but their ability to adapt to new data and tasks remains a challenging problem. The ability of a model to perform few-shot adaptation to a novel task is important for the scalability and deployment of machine learning models. Recent work has shown that the learned features in a neural network follow a normal distribution

    更新日期:2020-07-01
  • Policy Gradient Optimization of Thompson Sampling Policies
    arXiv.cs.LG Pub Date : 2020-06-30
    Seungki Min; Ciamac C. Moallemi; Daniel J. Russo

    We study the use of policy gradient algorithms to optimize over a class of generalized Thompson sampling policies. Our central insight is to view the posterior parameter sampled by Thompson sampling as a kind of pseudo-action. Policy gradient methods can then be tractably applied to search over a class of sampling policies, which determine a probability distribution over pseudo-actions (i.e., sampled

    更新日期:2020-07-01
  • SCE: Scalable Network Embedding from Sparsest Cut
    arXiv.cs.LG Pub Date : 2020-06-30
    Shengzhong Zhang; Zengfeng Huang; Haicang Zhou; Ziang Zhou

    Large-scale network embedding is to learn a latent representation for each node in an unsupervised manner, which captures inherent properties and structural information of the underlying graph. In this field, many popular approaches are influenced by the skip-gram model from natural language processing. Most of them use a contrastive objective to train an encoder which forces the embeddings of similar

    更新日期:2020-07-01
  • Online Dynamic Network Embedding
    arXiv.cs.LG Pub Date : 2020-06-30
    Haiwei Huang; Jinlong Li; Huimin He; Huanhuan Chen

    Network embedding is a very important method for network data. However, most of the algorithms can only deal with static networks. In this paper, we propose an algorithm Recurrent Neural Network Embedding (RNNE) to deal with dynamic network, which can be typically divided into two categories: a) topologically evolving graphs whose nodes and edges will increase (decrease) over time; b) temporal graphs

    更新日期:2020-07-01
  • Conditional GAN for timeseries generation
    arXiv.cs.LG Pub Date : 2020-06-30
    Kaleb E Smith; Anthony O Smith

    It is abundantly clear that time dependent data is a vital source of information in the world. The challenge has been for applications in machine learning to gain access to a considerable amount of quality data needed for algorithm development and analysis. Modeling synthetic data using a Generative Adversarial Network (GAN) has been at the heart of providing a viable solution. Our work focuses on

    更新日期:2020-07-01
  • Learning to Read through Machine Teaching
    arXiv.cs.LG Pub Date : 2020-06-30
    Ayon Sen; Christopher R. Cox; Matthew Cooper Borkenhagen; Mark S. Seidenberg; Xiaojin Zhu

    Learning to read words aloud is a major step towards becoming a reader. Many children struggle with the task because of the inconsistencies of English spelling-sound correspondences. Curricula vary enormously in how these patterns are taught. Children are nonetheless expected to master the system in limited time (by grade 4). We used a cognitively interesting neural network architecture to examine

    更新日期:2020-07-01
  • Model-Targeted Poisoning Attacks: Provable Convergence and Certified Bounds
    arXiv.cs.LG Pub Date : 2020-06-30
    Fnu Suya; Saeed Mahloujifar; David Evans; Yuan Tian

    Machine learning systems that rely on training data collected from untrusted sources are vulnerable to poisoning attacks, in which adversaries controlling some of the collected data are able to induce a corrupted model. In this paper, we consider poisoning attacks where there is an adversary who has a particular target classifier in mind and hopes to induce a classifier close to that target by adding

    更新日期:2020-07-01
  • Provable Online CP/PARAFAC Decomposition of a Structured Tensor via Dictionary Learning
    arXiv.cs.LG Pub Date : 2020-06-30
    Sirisha Rambhatla; Xingguo Li; Jarvis Haupt

    We consider the problem of factorizing a structured 3-way tensor into its constituent Canonical Polyadic (CP) factors. This decomposition, which can be viewed as a generalization of singular value decomposition (SVD) for tensors, reveals how the tensor dimensions (features) interact with each other. However, since the factors are a priori unknown, the corresponding optimization problems are inherently

    更新日期:2020-07-01
  • Efficient Continuous Pareto Exploration in Multi-Task Learning
    arXiv.cs.LG Pub Date : 2020-06-29
    Pingchuan Ma; Tao Du; Wojciech Matusik

    Tasks in multi-task learning often correlate, conflict, or even compete with each other. As a result, a single solution that is optimal for all tasks rarely exists. Recent papers introduced the concept of Pareto optimality to this field and directly cast multi-task learning as multi-objective optimization problems, but solutions returned by existing methods are typically finite, sparse, and discrete

    更新日期:2020-07-01
  • Fast OSCAR and OWL Regression via Safe Screening Rules
    arXiv.cs.LG Pub Date : 2020-06-29
    Runxue Bao; Bin Gu; Heng Huang

    Ordered Weighted $L_{1}$ (OWL) regularized regression is a new regression analysis for high-dimensional sparse learning. Proximal gradient methods are used as standard approaches to solve OWL regression. However, it is still a burning issue to solve OWL regression due to considerable computational cost and memory usage when the feature or sample size is large. In this paper, we propose the first safe

    更新日期:2020-07-01
  • Biologically Inspired Mechanisms for Adversarial Robustness
    arXiv.cs.LG Pub Date : 2020-06-29
    Manish V. Reddy; Andrzej Banburski; Nishka Pant; Tomaso Poggio

    A convolutional neural network strongly robust to adversarial perturbations at reasonable computational and performance cost has not yet been demonstrated. The primate visual ventral stream seems to be robust to small perturbations in visual stimuli but the underlying mechanisms that give rise to this robust perception are not understood. In this work, we investigate the role of two biologically plausible

    更新日期:2020-07-01
  • Efficient Algorithms for Device Placement of DNN Graph Operators
    arXiv.cs.LG Pub Date : 2020-06-29
    Jakub Tarnawski; Amar Phanishayee; Nikhil R. Devanur; Divya Mahajan; Fanny Nina Paravecino

    Modern machine learning workloads use large models, with complex structures, that are very expensive to execute. The devices that execute complex models are becoming increasingly heterogeneous as we see a flourishing of domain-specific accelerators being offered as hardware accelerators in addition to CPUs. These trends necessitate distributing the workload across multiple devices. Recent work has

    更新日期:2020-07-01
  • Unsupervised Calibration under Covariate Shift
    arXiv.cs.LG Pub Date : 2020-06-29
    Anusri Pampari; Stefano Ermon

    A probabilistic model is said to be calibrated if its predicted probabilities match the corresponding empirical frequencies. Calibration is important for uncertainty quantification and decision making in safety-critical applications. While calibration of classifiers has been widely studied, we find that calibration is brittle and can be easily lost under minimal covariate shifts. Existing techniques

    更新日期:2020-07-01
  • An EM Approach to Non-autoregressive Conditional Sequence Generation
    arXiv.cs.LG Pub Date : 2020-06-29
    Zhiqing Sun; Yiming Yang

    Autoregressive (AR) models have been the dominating approach to conditional sequence generation, but are suffering from the issue of high inference latency. Non-autoregressive (NAR) models have been recently proposed to reduce the latency by generating all output tokens in parallel but could only achieve inferior accuracy compared to their autoregressive counterparts, primarily due to a difficulty

    更新日期:2020-07-01
  • Hypergraph Random Walks, Laplacians, and Clustering
    arXiv.cs.LG Pub Date : 2020-06-29
    Koby HayashiGeorgia Institute of Technology; Sinan G. AksoyPacific Northwestern National Labs; Cheong Hee ParkChungnam National University; Haesun ParkGeorgia Institute of Technology

    We propose a flexible framework for clustering hypergraph-structured data based on recently proposed random walks utilizing edge-dependent vertex weights. When incorporating edge-dependent vertex weights (EDVW), a weight is associated with each vertex-hyperedge pair, yielding a weighted incidence matrix of the hypergraph. Such weightings have been utilized in term-document representations of text data

    更新日期:2020-07-01
  • Improving Uncertainty Estimates through the Relationship with Adversarial Robustness
    arXiv.cs.LG Pub Date : 2020-06-29
    Yao Qin; Xuezhi Wang; Alex Beutel; Ed H. Chi

    Robustness issues arise in a variety of forms and are studied through multiple lenses in the machine learning literature. Neural networks lack adversarial robustness -- they are vulnerable to adversarial examples that through small perturbations to inputs cause incorrect predictions. Further, trust is undermined when models give miscalibrated or unstable uncertainty estimates, i.e. the predicted probability

    更新日期:2020-07-01
  • Classification of cancer pathology reports: a large-scale comparative study
    arXiv.cs.LG Pub Date : 2020-06-29
    Stefano Martina; Leonardo Ventura; Paolo Frasconi

    We report about the application of state-of-the-art deep learning techniques to the automatic and interpretable assignment of ICD-O3 topography and morphology codes to free-text cancer reports. We present results on a large dataset (more than 80 000 labeled and 1 500 000 unlabeled anonymized reports written in Italian and collected from hospitals in Tuscany over more than a decade) and with a large

    更新日期:2020-07-01
  • Multi-Partition Embedding Interaction with Block Term Format for Knowledge Graph Completion
    arXiv.cs.LG Pub Date : 2020-06-29
    Hung Nghiep Tran; Atsuhiro Takasu

    Knowledge graph completion is an important task that aims to predict the missing relational link between entities. Knowledge graph embedding methods perform this task by representing entities and relations as embedding vectors and modeling their interactions to compute the matching score of each triple. Previous work has usually treated each embedding as a whole and has modeled the interactions between

    更新日期:2020-07-01
  • Multi-Head Attention: Collaborate Instead of Concatenate
    arXiv.cs.LG Pub Date : 2020-06-29
    Jean-Baptiste Cordonnier; Andreas Loukas; Martin Jaggi

    Attention layers are widely used in natural language processing (NLP) and are beginning to influence computer vision architectures. However, they suffer from over-parameterization. For instance, it was shown that the majority of attention heads could be pruned without impacting accuracy. This work aims to enhance current understanding on how multiple heads interact. Motivated by the observation that

    更新日期:2020-07-01
  • Handling Missing Data in Decision Trees: A Probabilistic Approach
    arXiv.cs.LG Pub Date : 2020-06-29
    Pasha Khosravi; Antonio Vergari; YooJung Choi; Yitao Liang; Guy Van den Broeck

    Decision trees are a popular family of models due to their attractive properties such as interpretability and ability to handle heterogeneous data. Concurrently, missing data is a prevalent occurrence that hinders performance of machine learning models. As such, handling missing data in decision trees is a well studied problem. In this paper, we tackle this problem by taking a probabilistic approach

    更新日期:2020-07-01
  • Scaling Symbolic Methods using Gradients for Neural Model Explanation
    arXiv.cs.LG Pub Date : 2020-06-29
    Subham Sekhar Sahoo; Subhashini Venugopalan; Li Li; Rishabh Singh; Patrick Riley

    Symbolic techniques based on Satisfiability Modulo Theory (SMT) solvers have been proposed for analyzing and verifying neural network properties, but their usage has been fairly limited owing to their poor scalability with larger networks. In this work, we propose a technique for combining gradient-based methods with symbolic techniques to scale such analyses and demonstrate its application for model

    更新日期:2020-07-01
  • Learning and Planning in Average-Reward Markov Decision Processes
    arXiv.cs.LG Pub Date : 2020-06-29
    Yi Wan; Abhishek Naik; Richard S. Sutton

    We introduce improved learning and planning algorithms for average-reward MDPs, including 1) the first general proven-convergent off-policy model-free control algorithm without reference states, 2) the first proven-convergent off-policy model-free prediction algorithm, and 3) the first learning algorithms that converge to the actual value function rather than to the value function plus an offset. All

    更新日期:2020-07-01
  • Dynamic Knapsack Optimization Towards Efficient Multi-Channel Sequential Advertising
    arXiv.cs.LG Pub Date : 2020-06-29
    Xiaotian Hao; Zhaoqing Peng; Yi Ma; Guan Wang; Junqi Jin; Jianye Hao; Shan Chen; Rongquan Bai; Mingzhou Xie; Miao Xu; Zhenzhe Zheng; Chuan Yu; Han Li; Jian Xu; Kun Gai

    In E-commerce, advertising is essential for merchants to reach their target users. The typical objective is to maximize the advertiser's cumulative revenue over a period of time under a budget constraint. In real applications, an advertisement (ad) usually needs to be exposed to the same user multiple times until the user finally contributes revenue (e.g., places an order). However, existing advertising

    更新日期:2020-07-01
  • Adversarial Learning for Debiasing Knowledge Graph Embeddings
    arXiv.cs.LG Pub Date : 2020-06-29
    Mario Arduini; Lorenzo Noci; Federico Pirovano; Ce Zhang; Yash Raj Shrestha; Bibek Paudel

    Knowledge Graphs (KG) are gaining increasing attention in both academia and industry. Despite their diverse benefits, recent research have identified social and cultural biases embedded in the representations learned from KGs. Such biases can have detrimental consequences on different population and minority groups as applications of KG begin to intersect and interact with social spheres. This paper

    更新日期:2020-07-01
  • Optimization Landscape of Tucker Decomposition
    arXiv.cs.LG Pub Date : 2020-06-29
    Abraham Frandsen; Rong Ge

    Tucker decomposition is a popular technique for many data analysis and machine learning applications. Finding a Tucker decomposition is a nonconvex optimization problem. As the scale of the problems increases, local search algorithms such as stochastic gradient descent have become popular in practice. In this paper, we characterize the optimization landscape of the Tucker decomposition problem. In

    更新日期:2020-07-01
Contents have been reproduced by permission of the publishers.
导出
全部期刊列表>>
自然科研论文编辑服务
ACS ES&T Engineering
ACS ES&T Water
屿渡论文,编辑服务
鲁照永
复旦大学
苏州大学
南京工业大学
南开大学
中科大
唐勇
跟Nature、Science文章学绘图
隐藏1h前已浏览文章
中洪博元
课题组网站
新版X-MOL期刊搜索和高级搜索功能介绍
ACS材料视界
x-mol收录
广东实验室
南京大学
陈永胜
南科大
刘尊峰
湖南大学
清华大学
王小野
中山大学化学工程与技术学院
试剂库存
天合科研
down
wechat
bug